Data Science Contractor
2022 - 2023Shell- Design solutions for carbon sequestration. Mined structured and unstructured data on the molecular processes driving the carbon cycle in the soil. Identified interventions to optimize the carbon cycle.
- Validated findings against the published literature (20M articles) using NLP.
- Developed interactive dashboard with the results and published to end users.
Technologies: Python 3, Scikit-learn, NumPy, Pandas, Git, Machine Learning, Artificial Intelligence (AI), Natural Language Processing (NLP), StatisticsMachine Learning CTO for carbon emission reduction project
2022 - 2022Carbon Connect Enterprise Strategies Inc.- Developed a platform for monitoring forest growth and carbon credit budgeting.
- Mined and segmented Lidar and satellite images for the identification of trees and tree growth.
- Built a dashboard using Streamlit in Python, deployed in GCP to allow the users query their data.
Technologies: Data Science, Machine Learning, Large-Scale Computing, CTOData Science Contractor
2020 - 2022AstraZeneca- Developed a machine learning workflow to leverage and interpret genetic data. This included parsing and preprocessing patient data, normalization, dimensionality reduction, statistical tests, and supervised analysis.
- Created a natural language solution for mining biomedical literature. The data was structured in an Elasticsearch database, cleaned, tokenized using the Natural Language Toolkit (NLTK), vectorized, and then used in a text classification framework.
- Built dashboards and UI using Streamlit in Python. Deployed using Nginx.
Technologies: Python 3, Bash Script, Data Science, Machine Learning, Natural Language Processing (NLP), Scikit-learn, Keras, TensorFlow, Streamlit, NGINX, Python, Data Analysis, Spotfire, Flask, Git, Data VisualizationData Science Contractor
2019 - 2020Arm- Built a machine learning framework for maximizing coverage in CPU verification. Development was in Python; deployed on HPC using the Slurm Workload Manager.
- Developed workflows leveraging adversarial learning using GANs and programmed in Python Keras.
- Addressed numerical optimization problems using genetic algorithms with a custom GA implementation.
Technologies: Python 3, Scikit-learn, Keras, TensorFlow, Generative Adversarial Networks (GANs), Bash, Jenkins, Git, Slurm Workload Manager, GitHub, Python, Deep Learning, Genetic Algorithms, Numerical Methods, Convex Optimization, Data VisualizationPrincipal Data Scientist
2016 - 2019UCB Celltech- Built machine learning workflows to predict patient response to candidate drugs. Developed in R.
- Led a team of three developers to create exploratory analytics solutions/dashboards to visualize high-dimensional data. Results were pre-calculated in R, then imported in TIBCO Spotfire.
- Designed machine learning solutions to predict drug activity in assays. Used LSTMs to model chemical structures as free text and applied methods from text classification.
Technologies: R, Python 3, Spotfire, Linux, H20, Keras, LSTM, Git, Python, Data Analysis, Data Analytics, Data Science, Machine Learning, Bioinformatics, Genomics, Data VisualizationPostdoctoral Research Fellow
2014 - 2016U.S. Food & Drug Administration- Developed a solution for predicting drug adverse events based on their transcriptomic profiles.
- Created a linear programming formulation to model the structure of directed graphs.
- Applied a solution to predict the adverse effects of new compounds.
Technologies: R, Linux, C, Slurm Workload Manager, Linear Optimization, NetworkX, Bioinformatics, Genomics, Drug Development, Python, Data Science, Data Analytics
Ioannis Melas
Data Scientist and Machine Learning Developer in Cambridge, United Kingdom
Member since March 30, 2021
Ioannis is a data scientist with expertise in prototyping, developing, and deploying data science and ML workflows that best leverage business data. This includes exploratory analysis such as dimensionality reduction, clustering, feature extraction, model fit/parameter estimation, and supervised analysis such as classification, regression. His expertise includes both structured and unstructured data (NLP). Notable clients include the U.S. Food & Drug Administration and AstraZeneca.
Ioannis is now available for hire
Portfolio
- ShellPython 3, Scikit-learn, NumPy, Pandas, Git, Machine Learning...
- Carbon Connect Enterprise Strategies Inc.Data Science, Machine Learning, Large-Scale Computing, CTO
- AstraZenecaPython 3, Bash Script, Data Science, Machine Learning...
Experience
- Data Science 12 years
- Bioinformatics 12 years
- Bash 12 years
- Machine Learning 12 years
- Scikit-learn 7 years
- Python 7 years
- Keras 5 years
- R 5 years
Availability
Full-time
Preferred Environment
Linux, Python 3, Flask-RESTful, Streamlit, Spotfire, Python, R, Bash
The most amazing...
...NLP solution I've developed was for the text summarization and classification of biomedical literature routinely used by research scientists.
Employment
Experience
- Mine Biomedical Literature Using Elasticsearch and NLP
Parsed and created a local copy of Pubmed, indexed using Elasticsearch, and created a UI using Streamlit to allow the user to query the whole of Pubmed, pull the papers that match their query, and perform basic NLP tasks using NLTK and Spacy.
- Framework for CPU Verification
Developed a machine learning framework for maximizing coverage in CPU verification. I leveraged adversarial learning using GANs and programmed in Python Keras. It was deployed using a command line API and is now routinely used in new products.
- Method for Predicting Efficacy of New Drugs
Developed machine learning workflows to predict patient response to candidate drugs. I integrated several data sources including free text datasets to built drug profiles, which I then used in a classification framework to predict their efficacy on patients. Developed in R. Results were ported to Spotfire for visualization.
Skills
Languages
Bash, Bash Script, Python, Python 3, R, SQL, CLibraries/APIs
Scikit-learn, Keras, NumPy, TensorFlow, LSTM, NLTK, Flask-RESTful, SpaCy, NetworkX, PySpark, PandasParadigms
Data SciencePlatforms
Jupyter Notebook, Linux, H20, Amazon Web Services (AWS), Google Cloud Platform (GCP), KubernetesIndustry Expertise
BioinformaticsOther
Machine Learning, Mathematical Modeling, Linear Optimization, Genomics, Numerical Methods, Numerical Simulations, Numerical Modeling, Streamlit, Natural Language Processing (NLP), Slurm Workload Manager, Data Analysis, Mixed-integer Linear Programming, Convex Optimization, Pharmaceuticals, Generative Adversarial Networks (GANs), Computational Physics, Deep Learning, Genetic Algorithms, Data Analytics, Drug Development, Gunicorn, Data Visualization, Artificial Intelligence (AI), Statistics, Large-Scale Computing, CTOTools
Spotfire, Git, NGINX, Jenkins, MATLAB, GitHub, Apache AirflowFrameworks
FlaskStorage
Elasticsearch
Education
- Ph.D. in Numerical Optimization, Machine Learning, Bioinformatics2008 - 2013National Technical University of Athens - Athens, Greece
- Master's Degree in Mechanical Engineering2003 - 2008National Technical University of Athens - Athens, Greece
